Trainings and Live sessions on the field of AI and ML. In this course we will explore DL thorugh Tensorflow, Keras, and Scikit-Learn.
 
Week 1-8: scikit-learn and Machine Learning Basics
Week 1: Introduction to Machine Learning and scikit-learn
Machine Learning Overview
Supervised vs. Unsupervised Learning
Train-test split, model selection
scikit-learn Basics
Loading datasets and basic data preprocessing
Week 2: Linear Regression
Linear Regression
Simple linear regression
Building a linear regression model with LinearRegression()
Week 3: Logistic Regression
Logistic Regression
Binary classification using logistic regression
Implementing LogisticRegression() for a simple task
Week 4: K-Nearest Neighbors (KNN)
KNN
Concept of KNN and distance metrics
Building and training a KNN model with KNeighborsClassifier()
Week 5: Decision Trees
Decision Trees
How decision trees work (entropy, information gain)
Building a decision tree with DecisionTreeClassifier()
Week 6: Random Forest
Random Forest
Introduction to Random Forests and ensemble learning
Implementing RandomForestClassifier()
Week 7: Model Evaluation
Model Evaluation
Metrics: accuracy, precision, recall, F1-score
Brief intro to cross-validation
Week 8: Recap of scikit-learn and Machine Learning
Recap Session
Review of key machine learning models learned so far
Hands-on exercises and practice
Review of model evaluation techniques
Week 9-17: Deep Learning with TensorFlow and Keras
Week 9: Introduction to Deep Learning Concepts
Neurons and Layers
Introduction to artificial neurons, weights, and biases
The structure of a neural network: input, hidden, and output layers
Activation Functions
Overview of activation functions: ReLU, Sigmoid, Softmax
When and why different activation functions are used
Week 10: Gradient Descent and Backpropagation
Gradient Descent
What gradient descent is and how it is used to optimize neural networks
Variants: Stochastic Gradient Descent (SGD), mini-batch gradient descent
Backpropagation
Explanation of how backpropagation works in updating weights
Introduction to loss functions (cross-entropy, mean squared error)
Week 11: Building a Simple Dense Neural Network
Dense Neural Networks
Introduction to dense (fully connected) layers
Building a simple dense neural network using Keras Sequential API
Week 12: Training Dense Neural Networks
Training Neural Networks
Setting up loss functions and optimizers (e.g., Adam, SGD)
Training and evaluating the model on a simple dataset
Week 13: Introduction to Convolutional Neural Networks (CNNs)
CNN Basics
Understanding convolution layers, filters, strides, and padding
Max pooling layers, flatten layer, and dense layers
Implementing a simple CNN for image classification (e.g., MNIST dataset)
Week 14: Training CNN Models
Training CNNs
Concepts of regularization (dropout, batch normalization) and data augmentation
Training a CNN model on a basic dataset (MNIST or CIFAR-10)
Week 15-21: Tic-Tac-Toe AI Project, Test Prep, and AI Overview
Week 15: Tic-Tac-Toe Game Logic
Building the Game
Implementing Tic-Tac-Toe game logic with Python
Basics of decision-making in games
Week 16: Tic-Tac-Toe AI Implementation
Minimax Algorithm
Implementing Minimax for optimal game strategy in Tic-Tac-Toe
Adding different difficulty levels to the AI
Week 17: Playing Tic-Tac-Toe in the Console
Game Testing
Playing the game with the AI directly in the Python console
Testing and refining the AI’s performance through interaction
Week 18: Test Preparation and Review
Review Session
Recap of major concepts from the course
Key topics: machine learning models, neural networks, CNNs, gradient descent, activation functions
Practice questions and clarification of doubts
Week 19: AI Concept and Theory Test
Test Overview
The test will cover key concepts from the course:
Machine learning algorithms (regression, classification, decision trees, etc.)
Neural networks (dense layers, CNNs)
Concepts like gradient descent, activation functions, backpropagation
This test will assess understanding of both theoretical and practical elements covered throughout the course.
Final Week: Overview of AI Fields
Week 20: Overview of AI Fields
Introduction to Other AI Topics (No Coding)
Generative AI: Overview of GANs and other generative models
TinyML: Introduction to running ML models on microcontrollers and small devices
Edge AI: How AI runs on edge devices
Ethics in AI: Brief discussion on fairness, bias, and responsible AI